Metal Mantra / AGENT INTELLIGENCEPublic evidence reportAUTOMATED SIGNAL. NOT CERTIFICATION.
Metal Mantra
Run free scan
Metal Mantra
Run free scan

Public agent signals. Clear evidence boundaries.

PUBLIC REPORT · ADDED BY METAL MANTRA / AGENT SIGNAL v0.2

memori.

Automated source and domain checks for memorilabs/memori.

Metal Mantra scanned this public repository on its own initiative; the maintainer did not submit it. Maintainers: scan the repository yourself to take this report over, or contact us.

Inspect GitHub source

17.1k starsOtherpushed 9d ago

0community interest

Votes show community interest, not safety. They never change this score.

AUTOMATED SIGNAL49/100CCCNot security certification
START HERE

Critical findings need attention.

Critical finding · details withheld for 30 days

Inspect the findings
WHAT THIS DOES NOT ESTABLISH

Runtime safety, real-world agent capability, fitness for your use case or independent certification.

Scan scope200 / 220Partial eligible-file selection · not the entire repository
Recorded findings18Heuristic matches requiring human review
SnapshotOct 12, 2026UTC · engine 0.4.0
DNS at scan timeUnverifiedDomain control is not security certification
01 / KNOW THE REPOSITORY

What the source
actually tells us.

Structured, cited information from the scanned archive. Repository-authored claims are labeled and never treated as verified capabilities.

INSPECTED SOURCE200 / 220Partial selection
READMEReadRepository-authored information
MANIFESTS2LICENSE, pyproject.toml

Who it is for

  • Stated use case · repository says · unreviewed

    For more examples and demos, check out the Memori Cookbook.

    README.md:266

What it can do

No explicit capability or integration was extracted; that does not mean none exists.

What adoption takes

  • Stated prerequisite · manifest declares · unreviewed

    Manifest declares Python >=3.10 as a requirement.

    pyproject.toml:12
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on aiohttp.

    pyproject.toml:32
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on botocore.

    pyproject.toml:33
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on faiss-cpu.

    pyproject.toml:34
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on grpcio.

    pyproject.toml:35
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on numpy.

    pyproject.toml:36
  • Declared dependency · manifest declares · unreviewed

    Declares a dependency on protobuf.

    pyproject.toml:37

Limits and terms

  • Declared license · manifest declares · unreviewed

    A license or copying file is present; its terms have not been reviewed.

    LICENSE:1

Observed technical context

TypeScript · 53 selected filesJavaScript · 3 selected filesPython · 144 selected filesModel API reference · static onlyTool-calling reference · static only

These are references in selected source files, not proof that a feature works at runtime.

Read from commit 574b1ea at Oct 12, 2026, 5:33 AM UTC. Source links open that exact commit. Repository statements are unreviewed and do not affect the score.

02 / FINDINGS FIRST

What needs
a closer look.

Critical details are withheld publicly for the first 30 days after a scan. A matched pattern is a lead for investigation, not a confirmed vulnerability.

Dependencies: 26 exact runtime versions from uv.lock checked against OSV.dev on Oct 12, 2026; 6 with known advisories. Reachability is not checked.

18 findings
CRITICAL

Critical finding · details withheld for 30 days

SEC001 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

SEC001 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

SEC002 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
CRITICAL

Critical finding · details withheld for 30 days

SEC002 · Security & privacy

Details are withheld from public view for 30 days after the scan. The owner can see them in full.

SUGGESTED ACTION

Review the private assessment and address the finding.

[location embargoed] · location unavailable
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

examples/cockroachdb/main.py:27
MAJOR

LLM request without token ceiling

REL001 · Guardrails & loop control

A model request does not set a maximum output length. One unusual input can produce a very long, expensive response.

SUGGESTED ACTION

Set max_tokens or the provider's equivalent on each model call.

examples/cockroachdb/main.py:36
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

examples/cockroachdb/main.py:27
MAJOR

LLM output without runtime schema

SCH001 · Schema & tooling

Model output is used without being checked against a schema. Unexpected or malformed output can break later steps or be trusted when it should not be.

SUGGESTED ACTION

Validate model output with Zod, JSON Schema, Pydantic or provider structured output.

examples/cockroachdb/main.py:36
MAJOR

Model call without fallback

EFF001 · Token & cost efficiency

A model call has no visible fallback. If the provider fails or is rate limited, the whole agent fails with it.

SUGGESTED ACTION

Configure a secondary model or explicit fallback path for provider failures.

examples/cockroachdb/main.py:27
MAJOR

Domain ownership not verified

TRUST001 · Entity trust

Metal Mantra could not confirm that the owner controls the stated domain. The domain may belong to someone else.

SUGGESTED ACTION

Verify the domain using the Metal Mantra DNS TXT challenge.

memorilabs.ai · location unavailable
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

aiohttp 3.14.1 (PyPI) has known advisories: GHSA-cq5v-8q36-5273, GHSA-mfx4-hv73-q22v, GHSA-mq44-7p77-q5h7, PYSEC-2026-3545, PYSEC-2026-3546 (highest severity high). AIOHTTP: Out-of-bounds heap read in C HTTP response parser error path (malformed chunked response)

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:52
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

protobuf 5.29.5 (PyPI) has known advisories: GHSA-7gcm-g887-7qv7, PYSEC-2026-1805 (highest severity high). protobuf affected by a JSON recursion depth bypass

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:1158
MAJOR

Dependency with a high-severity advisory

DEP001 · Security & privacy

urllib3 2.5.0 (PyPI) has known advisories: GHSA-2xpw-w6gg-jr37, GHSA-38jv-5279-wg99, GHSA-8988-9cw3-xx77, GHSA-gm62-xv2j-4w53, GHSA-qccp-gfcp-xxvc (highest severity high). urllib3 streaming API improperly handles highly compressed data

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:327
MINOR

Privacy Policy link not confirmed

TRUST003 · Entity trust

No privacy policy link was found on the stated homepage. Buyers cannot see how the vendor handles their data.

SUGGESTED ACTION

Expose a clear Privacy Policy link on the official homepage.

memorilabs.ai · location unavailable
MINOR

Terms link not confirmed

TRUST004 · Entity trust

No terms link was found on the stated homepage. Buyers cannot see the conditions that apply to using the service.

SUGGESTED ACTION

Expose a clear Terms link on the official homepage.

memorilabs.ai · location unavailable
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

idna 3.11 (PyPI) has known advisories: GHSA-65pc-fj4g-8rjx, PYSEC-2026-215 (highest severity moderate). Internationalized Domain Names in Applications (IDNA): Specially crafted inputs to idna.encode() can bypass CVE-2024-3651 fix

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:247
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

multidict 6.7.0 (PyPI) has a known advisory: GHSA-54p9-h82j-f925 (highest severity moderate). Multidict: Reference leak in CIMultiDict/MultiDict items-view union and subtraction

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:61
MINOR

Dependency with a known advisory

DEP002 · Security & privacy

requests 2.32.5 (PyPI) has known advisories: GHSA-gc5v-m9x4-r6x2, PYSEC-2026-2275 (highest severity moderate). Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility function

SUGGESTED ACTION

Upgrade to a fixed version listed in the advisory and regenerate the lockfile.

uv.lock:401
03 / EVIDENCE & LIMITS

The boundary
is part of the result.

What was scanned
200 of 220 eligible files · Partial selection.
Supported static source patterns and domain checks; no runtime execution.
What remains unknown
Unscanned files, external dependencies, production configuration, actual agent behavior and evidence beyond the configured checks.
Source location
Links open the current repository HEAD. Source may have changed since this snapshot.
Something looks wrong?
Tell us if a finding, scope or claim on this report needs a correction. Report a problem with this report
Entity trust · 15% of v0.2
Includes DNS ownership, HTTPS and policy evidence. Verification is domain control, not a security certificate.
DNS: unverifiedHTTPS: availablePrivacy: not confirmedTerms: not confirmed
04 / THE METHOD BEHIND THE NUMBER

Open the
calculation.

Each pillar starts at 100. Rule deductions reduce its score; weights determine the overall contribution.

01

Security & privacy

10 findings · 25% weight
0/1000.0 pts
02

Guardrails & loop control

2 findings · 25% weight
76/10019.0 pts
03

Schema & tooling

2 findings · 20% weight
68/10013.6 pts
04

Token & cost efficiency

1 findings · 15% weight
86/10012.9 pts
05

Entity trust

3 findings · 15% weight
25/1003.8 pts
Inspect the current standard
USER REPORTS

Did memori work for people?

No user reports yet.

Each report is one signed-in GitHub account saying what happened. We do not verify that the account ran the agent, and reports never change the automated score or grade. For a security problem, use the disclosure page instead of a public note.

Sign in with GitHub to add a report

SHARE THE EVIDENCE

A signal.
Not a seal.

Share the full report so its scope and limits travel with the score.

Metal Mantra automated signal 49/100, not certified